---
key: mechanic/phone-camera--family-hands
type: mechanic
id: phone-camera--family-hands
lang: en
title: 'Hands, fingers and hand gestures'
summary: >-
The camera estimates hand and finger positions. MediaPipe provides hand
landmarks; gesture rules must handle occlusion and tracking loss.
updatedAt: '2026-10-22'
status: active
url: 'https://gamemechanics.pro/en/knowledge/mechanic/phone-camera--family-hands/'
jsonUrl: >-
https://gamemechanics.pro/api/v1/knowledge/en/mechanic/phone-camera--family-hands.json
markdownUrl: >-
https://gamemechanics.pro/content/knowledge/en/mechanic/phone-camera--family-hands.md
aliases: []
tags:
- Phone camera interactions
- Mechanics catalog
sourceIds:
- source-a9a2e810611ce816
- source-f13cbf1738c5a87a
sources:
- id: source-a9a2e810611ce816
title: MediaPipe Hand Landmarker
url: >-
https://developers.google.com/edge/mediapipe/solutions/vision/hand_landmarker
verifiedAt: null
- id: source-f13cbf1738c5a87a
title: MediaPipe Hand Landmarker
url: 'https://ai.google.dev/edge/mediapipe/solutions/vision/hand_landmarker'
verifiedAt: null
relations: []
placements:
- catalogId: phone-camera
id: family-hands
title: Phone camera interactions
url: 'https://gamemechanics.pro/en/mechanics/phone-camera/#family-hands'
categoryIds:
- section-1
supersededBy: []
attributes:
preview:
updatedAt: '2026-10-22'
title: 'Hands, fingers and hand gestures'
description: >-
The camera estimates hand and finger positions. MediaPipe provides hand
landmarks; gesture rules must handle occlusion and tracking loss.
image:
src: images/mechanics/camera-mp-hand.webp
width: 1024
height: 574
game: MediaPipe Hand Landmarker
sourceUrl: 'https://ai.google.dev/edge/mediapipe/solutions/vision/hand_landmarker'
originalUrl: >-
https://ai.google.dev/static/mediapipe/images/solutions/examples/hand_landmark.png
credit: Google / original image contributors
rights: >-
© Google / original image contributors. Official documentation or
publisher-distributed image; respective rights retained. Excluded from
portal MIT and CC BY 4.0.
caption: 'MediaPipe Hand Landmarker: hand landmarks over the source image'
alt: 'MediaPipe Hand Landmarker: hand landmarks over the source image'
markers:
- x: 45
'y': 55
label: Points and connections describe finger and hand positions
tips:
- Do not promise arbitrary gesture understanding without a tested model.
examples:
- title: MediaPipe Hand Landmarker
url: 'https://ai.google.dev/edge/mediapipe/solutions/vision/hand_landmarker'
endsAt: null
provenance: >-
Original editorial design catalog consolidated from project discussions on
2026-10-20. Complete discussion item lists and contextual limitations are
preserved; linked primary sources support specific techniques, not the entire
classification. English translation was prepared with machine assistance and
editorial review.
license: CC-BY-4.0
codeLicense: MIT
attribution: gamemechanics.pro contributors
catalogKey: catalog/phone-camera
---
# Hands, fingers and hand gestures
id: phone-camera--family-hands
type: mechanic
key: mechanic/phone-camera--family-hands
lang: en
status: active
url: https://gamemechanics.pro/en/knowledge/mechanic/phone-camera--family-hands/
The camera estimates hand and finger positions. MediaPipe provides hand landmarks; gesture rules must handle occlusion and tracking loss.
## At a glance
[MediaPipe Hand Landmarker](https://ai.google.dev/edge/mediapipe/solutions/vision/hand_landmarker) · © Google / original image contributors. Official documentation or publisher-distributed image; respective rights retained. Excluded from portal MIT and CC BY 4.0.
1. Points and connections describe finger and hand positions
- Do not promise arbitrary gesture understanding without a tested model.
- [MediaPipe Hand Landmarker](https://ai.google.dev/edge/mediapipe/solutions/vision/hand_landmarker)
## How it works
Hands give positional, discrete and continuous commands. You need to take into account mirroring, overlapping hands, and falling out of frame. The position of the fingers does not mean that the system understands any sign language.
## Variants
### Variants and applications
- Finger pointing. Action: Move your fingertip and hover the virtual pointer. Application: Touchless menu, drawing, target selection. Technologies: Recognition or machine learning model.
- Pinch. Action: Bring your thumb and index finger together to grasp, unclench to release. Application: Drag and drop, assembly, working with virtual objects. Technologies: Recognition or machine learning model.
- Fist and palm. Action: Squeeze and unclench the hand to change the binary state. Application: Shield and attack, holding an object, launching an effect. Technologies: Recognition or machine learning model.
- Number of fingers. Action: Show a number with your fingers in a consistent set of gestures. Application: Arithmetic, answer choice, numeric code. Technologies: Recognition or machine learning model.
- Turn the palm. Action: Change the angle of the hand to rotate a handle, shield or object. Application: Spatial puzzle, device control, gestural music. Technologies: Recognition or machine learning model.
- Two-handed zooming. Action: Spread, bring together and rotate two brushes. Application: Sizing and rotating an object, stretching a field, sculpting. Technologies: Recognition or machine learning model.
- Gesture trajectory. Action: Run a sequence of movements with your palm or finger. Application: Spells, dance game for hands, robot commands. Technologies: Recognition or machine learning model.
- Manual pantomime. Action: Reproduce a gesture from a limited trained vocabulary. Application: Rock, paper, scissors, charades, learning selected gestures. Technologies: Recognition or machine learning model; Own algorithm.
## Context and limits
Games, learning, creativity and interactive applications. Author's systematization of game rules based on proven technical capabilities. Examples are application ideas and not statements of released products.
## Connected materials
## Sources and provenance
Original editorial design catalog consolidated from project discussions on 2026-10-20. Complete discussion item lists and contextual limitations are preserved; linked primary sources support specific techniques, not the entire classification. English translation was prepared with machine assistance and editorial review.
- [MediaPipe Hand Landmarker](https://developers.google.com/edge/mediapipe/solutions/vision/hand_landmarker) (id: source-a9a2e810611ce816)
- [MediaPipe Hand Landmarker](https://ai.google.dev/edge/mediapipe/solutions/vision/hand_landmarker) (id: source-f13cbf1738c5a87a)
CC-BY-4.0 · gamemechanics.pro contributors